Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2682482800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4befdd3f09e9c679dc40530559fabbaa4e830310fd3991e4bbaa3311dcd424c9
|
| 3 |
size 2682482800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5365108834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71dba3b96b8d272909517c3dac072631e8a7f11327952878a48a37a3af524ce8
|
| 3 |
size 5365108834
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:964109b969e887b4efbe365a0f65c7d5f4c4d5f54fa26ef42c5f637a18eae37f
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863cf4a7956086b9fd348589f422e8af87ea5d78b5c7d0e595c32a5aaf7e77e5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -157,6 +157,81 @@
|
|
| 157 |
"eval_samples_per_second": 57.901,
|
| 158 |
"eval_steps_per_second": 28.95,
|
| 159 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
}
|
| 161 |
],
|
| 162 |
"logging_steps": 50,
|
|
@@ -176,7 +251,7 @@
|
|
| 176 |
"attributes": {}
|
| 177 |
}
|
| 178 |
},
|
| 179 |
-
"total_flos":
|
| 180 |
"train_batch_size": 2,
|
| 181 |
"trial_name": null,
|
| 182 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9972065305108946,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 753,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 157 |
"eval_samples_per_second": 57.901,
|
| 158 |
"eval_steps_per_second": 28.95,
|
| 159 |
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.190700850456267,
|
| 163 |
+
"grad_norm": 1.057379961013794,
|
| 164 |
+
"learning_rate": 7.808764940239044e-05,
|
| 165 |
+
"loss": 1.241,
|
| 166 |
+
"step": 550
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.190700850456267,
|
| 170 |
+
"eval_loss": 1.25983726978302,
|
| 171 |
+
"eval_runtime": 14.6655,
|
| 172 |
+
"eval_samples_per_second": 57.823,
|
| 173 |
+
"eval_steps_per_second": 28.911,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.3893475696815445,
|
| 178 |
+
"grad_norm": 1.0341771841049194,
|
| 179 |
+
"learning_rate": 7.609561752988048e-05,
|
| 180 |
+
"loss": 1.2102,
|
| 181 |
+
"step": 600
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.3893475696815445,
|
| 185 |
+
"eval_loss": 1.2425962686538696,
|
| 186 |
+
"eval_runtime": 14.6716,
|
| 187 |
+
"eval_samples_per_second": 57.799,
|
| 188 |
+
"eval_steps_per_second": 28.899,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.587994288906822,
|
| 193 |
+
"grad_norm": 0.9421936869621277,
|
| 194 |
+
"learning_rate": 7.410358565737052e-05,
|
| 195 |
+
"loss": 1.2018,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.587994288906822,
|
| 200 |
+
"eval_loss": 1.2194551229476929,
|
| 201 |
+
"eval_runtime": 14.6762,
|
| 202 |
+
"eval_samples_per_second": 57.781,
|
| 203 |
+
"eval_steps_per_second": 28.89,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.7866410081321,
|
| 208 |
+
"grad_norm": 1.0019429922103882,
|
| 209 |
+
"learning_rate": 7.211155378486057e-05,
|
| 210 |
+
"loss": 1.1846,
|
| 211 |
+
"step": 700
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.7866410081321,
|
| 215 |
+
"eval_loss": 1.2068556547164917,
|
| 216 |
+
"eval_runtime": 14.7447,
|
| 217 |
+
"eval_samples_per_second": 57.512,
|
| 218 |
+
"eval_steps_per_second": 28.756,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.985287727357378,
|
| 223 |
+
"grad_norm": 1.0412020683288574,
|
| 224 |
+
"learning_rate": 7.01195219123506e-05,
|
| 225 |
+
"loss": 1.1678,
|
| 226 |
+
"step": 750
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.985287727357378,
|
| 230 |
+
"eval_loss": 1.199570655822754,
|
| 231 |
+
"eval_runtime": 17.8039,
|
| 232 |
+
"eval_samples_per_second": 47.63,
|
| 233 |
+
"eval_steps_per_second": 23.815,
|
| 234 |
+
"step": 750
|
| 235 |
}
|
| 236 |
],
|
| 237 |
"logging_steps": 50,
|
|
|
|
| 251 |
"attributes": {}
|
| 252 |
}
|
| 253 |
},
|
| 254 |
+
"total_flos": 1.2018630583228826e+17,
|
| 255 |
"train_batch_size": 2,
|
| 256 |
"trial_name": null,
|
| 257 |
"trial_params": null
|